tui

A Bell Labs film in which Dr. J.N. Shive uses a mechanical wave machine to demonstrate reflection, standing waves, resonance and impedance matching. He includes some equations but relies mostly on real-world examples a layperson can follow.

Bill Hammack of engineerguy introduces his series on Michael Faraday's lectures on The Chemical History of a Candle. He describes the free companion book and the commentary and caption features that help modern viewers.

Royal Institution lecture by Dr Kate Lancaster on the most powerful lasers in the world and the extreme conditions they create. It includes live demonstrations and covers applications from industry to fusion.

Richard Hamming's 1995 lecture on n-dimensional space, showing how geometric intuition about spheres and cubes breaks down in high dimensions. It is part of his course on learning to learn.

Andrej Karpathy's first Neural Networks: Zero to Hero lecture, which builds micrograd, a tiny autograd engine, from scratch in Python. It explains backpropagation and neural network training step by step, assuming only basic Python and some high-school calculus.

Part 1 of a lecture by physicist Albert Bartlett on the exponential function and its consequences for population growth, resource use and energy. It argues that steady growth rates quickly lead to enormous quantities.

Physicist Carlo Rovelli gives a public lecture at the Royal Institution on how our understanding of time has changed, from Boltzmann and Einstein to quantum theory and loop quantum gravity. He blends physics, philosophy and art to argue that time is stranger than everyday intuition suggests.

The first lecture of Francis Su's Harvey Mudd real analysis course, covering the construction of the rational numbers. It begins a full lecture series that follows a standard analysis text.

Geoffrey Hinton's 2025 Royal Institution Discourse on what AI has learned from biological intelligence and how it might surpass it. He explains neural networks and argues that human language use resembles what backpropagation-trained networks do.

Milton Friedman explains why the US tax code is enormously complex and why meaningful reform is unlikely. He argues that politicians profit from the complexity, since tax breaks are products they sell and the code works as a tool of reward and punishment. The clip is about 14 minutes from his lecture series.

A segment from Carl Sagan's original Cosmos explaining the fourth spatial dimension through analogy with a two-dimensional world and shadow projection.

Sasha Rush surveys linear RNNs and state space models as replacements for attention in transformer-style models, in a talk for MLSys. It covers the foundational preliminaries and predates Mamba.

Michael Betancourt's lecture at MLSS Iceland 2014 on efficient Bayesian inference with Hamiltonian Monte Carlo. It covers MCMC concepts and motivation and the problems of sampling in high-dimensional distributions.

A university lecture from CS480/680 by Pascal Poupart on attention mechanisms and transformer networks, worked through on a chalkboard.

A 3Blue1Brown live lockdown math episode asking what Euler's formula e^(pi i) is actually saying. It builds intuition through exponentials, rotation and vectors landing on the unit circle.

Paul Graham's lecture in the 'How to Start a Startup' course, covering counterintuitive parts of startups and how to have ideas. It is the video form of his essay 'Before the Startup'.